© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11278
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or policy matters

    oai_token-act-pair · gpt-3.5-turbo

    references to legal concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SEN
    -0.74
     Axel
    -0.69
     metic
    -0.69
     reflex
    -0.69
     Qi
    -0.69
     QC
    -0.67
     Slug
    -0.67
     VS
    -0.67
     Esper
    -0.66
     Villa
    -0.65
    POSITIVE LOGITS
    every
    1.20
    everything
    1.17
    ever
    1.16
    different
    1.15
    other
    1.14
    nob
    1.13
    outside
    1.13
    none
    1.13
    sure
    1.13
    double
    1.12
    Activations Density 0.127%

    No Known Activations